Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43700
    Prev
    Next
    INDEX
    Explanations

    optimization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhythms
    -0.09
    habit
    -0.08
    _spacing
    -0.08
    徴
    -0.08
     sympathy
    -0.08
    စ
    -0.08
     Engel
    -0.08
    射
    -0.08
    РА
    -0.08
    Особ
    -0.08
    POSITIVE LOGITS
    求
    0.08
     reached
    0.08
     Problems
    0.08
     поиска
    0.08
     Landsc
    0.07
    blems
    0.07
    gon
    0.07
     problems
    0.07
     求
    0.07
     unsuccess
    0.07
    Activations Density 0.008%

    No Known Activations